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. 1383
    Prev
    Next
    INDEX
    Explanations

    mentions of obligations or requirements

    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
    1331
    +0.15
    0.6%
    680
    +0.12
    0.5%
    411
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1331
    +0.15
    0.04
    239
    +0.12
    0.04
    411
    +0.12
    0.04
    Negative Logits
     Meksi
    -1.10
     silikon
    -0.92
     karton
    -0.92
     seksi
    -0.92
     optik
    -0.89
     saar
    -0.85
     keramik
    -0.85
     siena
    -0.83
     Abbé
    -0.82
     maksi
    -0.82
    POSITIVE LOGITS
     must
    1.06
    must
    1.02
     Must
    0.93
    Must
    0.88
     MUST
    0.88
    MUST
    0.77
     doit
    0.67
     mustache
    0.61
     musí
    0.60
     mustard
    0.59
    Activations Density 0.082%

    No Known Activations