© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2740
    Prev
    Next
    INDEX
    Explanations

    information related to specific exact details and descriptions

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.08
    0.3%
    1491
    +0.07
    0.2%
    1328
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1780
    +0.08
    0.02
    1446
    +0.07
    0.02
    1363
    +0.06
    0.02
    Negative Logits
    <bos>
    -1.52
     inaugurate
    -0.60
    finally
    -0.60
    šech
    -0.58
    SPECTION
    -0.58
    bigsqcup
    -0.56
    MarshalTo
    -0.56
     finally
    -0.55
     صوتيه
    -0.54
     disarm
    -0.53
    POSITIVE LOGITS
     exact
    2.10
    exact
    2.07
     Exact
    1.96
     EXACT
    1.95
    Exact
    1.71
     exacte
    1.42
    EXACT
    1.23
     Approximate
    1.18
    approximate
    1.16
     approximate
    1.14
    Activations Density 0.041%

    No Known Activations