© 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 EvalsExportsAPI 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. 14862
    Prev
    Next
    INDEX
    Explanations

    descriptions of step-by-step actions or procedures

    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
    776
    +0.13
    0.4%
    381
    +0.10
    0.3%
    331
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    331
    +0.13
    0.07
    1491
    +0.10
    0.06
    421
    +0.10
    0.05
    Negative Logits
     churrasco
    -0.68
     churras
    -0.68
    °;
    -0.66
     Cæsar
    -0.65
     Darío
    -0.65
     cytok
    -0.64
    “…”
    -0.63
     tortas
    -0.62
     myn
    -0.62
     Mónica
    -0.62
    POSITIVE LOGITS
    There
    0.75
     There
    0.74
    there
    0.73
     there
    0.71
    THERE
    0.69
     THERE
    0.68
    earcher
    0.53
     exists
    0.51
     hasn
    0.51
     كومونز
    0.51
    Activations Density 0.155%

    No Known Activations