© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 2152
    Prev
    Next
    INDEX
    Explanations

    technical terms related to internet usage and regulatory bodies, specific legal terms, and financial entities such as companies and commissions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.10
    0.4%
    1793
    +0.09
    0.4%
    1935
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.10
    0.08
    1043
    +0.09
    0.07
    254
    +0.08
    0.07
    Negative Logits
     intersper
    -1.52
     endow
    -1.16
     vainly
    -1.15
     gratify
    -1.14
     unspeak
    -1.10
     impelled
    -1.08
     rascal
    -1.07
     strove
    -1.07
     quitted
    -1.05
     underval
    -1.04
    POSITIVE LOGITS
     kosme
    1.13
     poliuret
    1.09
     plak
    1.06
     meras
    1.01
     alkoh
    1.01
     minimalis
    1.01
     miniatura
    1.00
     marte
    1.00
     kac
    1.00
     lomb
    0.99
    Activations Density 0.939%

    No Known Activations