© 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. 2745
    Prev
    Next
    INDEX
    Explanations

    names of a person "Anna."

    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
    1178
    +0.12
    0.4%
    1334
    +0.11
    0.4%
    1222
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.12
    0.04
    1343
    +0.11
    0.04
    690
    +0.10
    0.04
    Negative Logits
    <bos>
    -0.90
     satellite
    -0.67
    atellite
    -0.65
    |}
    -0.64
    createQuery
    -0.63
    <!--
    -0.63
    AutoScaleMode
    -0.61
    َ
    -0.61
    mtext
    -0.61
    แม
    -0.61
    POSITIVE LOGITS
     impractica
    1.75
     sovere
    1.74
     Juf
    1.70
     disagre
    1.68
     pamph
    1.68
     unlaw
    1.66
     reluct
    1.66
     fortn
    1.65
     unwarran
    1.62
     maneu
    1.58
    Activations Density 0.236%

    No Known Activations