© 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. 1317
    Prev
    Next
    INDEX
    Explanations

    references to specific names or people

    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
    1896
    +0.12
    0.4%
    1178
    +0.12
    0.4%
    313
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1896
    +0.12
    0.03
    1343
    +0.12
    0.04
    1120
    +0.10
    0.03
    Negative Logits
     shuddered
    -0.85
     tayo
    -0.79
     peered
    -0.70
     akong
    -0.67
     shivered
    -0.66
     natin
    -0.65
    /**
    -0.63
     knelt
    -0.63
     silang
    -0.61
     kayo
    -0.60
    POSITIVE LOGITS
     Sig
    2.52
    Sig
    2.25
     sig
    2.04
     SIG
    2.04
     Sigma
    1.86
    sig
    1.80
    SIG
    1.79
     sigma
    1.52
    SIGMA
    1.35
    Sigma
    1.34
    Activations Density 0.267%

    No Known Activations