Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15256
    Prev
    Next
    INDEX
    Explanations

    steps or instructions in a technical or mechanical process

    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
    1385
    +0.13
    0.4%
    906
    +0.08
    0.2%
    1150
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.13
    0.05
    724
    +0.08
    0.04
    335
    +0.07
    0.03
    Negative Logits
     pessi
    -1.11
     wien
    -1.03
     strick
    -1.02
     emphat
    -1.02
     accla
    -1.01
     madonna
    -0.99
     ardu
    -0.97
     bayern
    -0.97
     stockholm
    -0.96
     errone
    -0.95
    POSITIVE LOGITS
     underneath
    0.82
     underlying
    0.75
     reveal
    0.67
     beneath
    0.65
     behind
    0.64
     inside
    0.63
     revealing
    0.61
     revealed
    0.61
    underlying
    0.58
     hidden
    0.58
    Activations Density 0.364%

    No Known Activations