© 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. 0-RES-JB
    11. 1690
    Prev
    Next
    INDEX
    Explanations

    terms related to names or titles of people or entities

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1095
    +0.07
    0.2%
    1482
    +0.07
    0.2%
    834
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.07
    0.04
    283
    +0.07
    0.01
    1363
    +0.07
    0.03
    Negative Logits
     reluct
    -1.33
     apprehen
    -1.29
     vainly
    -1.29
     shenan
    -1.24
     disagre
    -1.24
     intersper
    -1.24
     unspeak
    -1.23
     volunte
    -1.20
     impra
    -1.19
     reconno
    -1.18
    POSITIVE LOGITS
    iff
    1.99
    IF
    1.85
    IFF
    1.59
    if
    1.44
     IF
    1.35
    iffs
    1.32
    ifs
    1.22
    iffe
    1.07
    ife
    1.03
    tif
    1.00
    Activations Density 0.207%

    No Known Activations