© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 16296
    Prev
    Next
    INDEX
    Explanations

    financial and legal information or irregularities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1013
    +0.18
    0.6%
    1150
    +0.13
    0.4%
    1978
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1965
    +0.18
    0.05
    1720
    +0.13
    0.03
    609
    +0.10
    0.04
    Negative Logits
     dises
    -1.05
     §.
    -0.98
     fte
    -0.94
     doman
    -0.94
     fign
    -0.93
     „,
    -0.93
     thut
    -0.92
     nece
    -0.92
     desir
    -0.92
     robus
    -0.90
    POSITIVE LOGITS
    0
    0.69
    -$
    0.61
    /$
    0.60
     ($
    0.56
     per
    0.54
    ($
    0.53
    5
    0.53
    4
    0.53
    .
    0.53
    $,
    0.52
    Activations Density 0.130%

    No Known Activations