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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 808
    Prev
    Next
    INDEX
    Explanations

    terms related to biological and medical research, specifically regarding cells and their functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.26
    1.2%
    1150
    +0.12
    0.5%
    2034
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.26
    0.08
    2034
    +0.12
    0.12
    1842
    +0.12
    0.06
    Negative Logits
    <bos>
    -3.47
    Билгалдахарш
    -0.84
    Примеча
    -0.83
    /***
    
    -0.82
    uxxxx
    -0.81
    MarshalTo
    -0.81
    ⓧ
    -0.75
    AsUp
    -0.75
    delwed
    -0.73
    fromnode
    -0.69
    POSITIVE LOGITS
     jaya
    1.06
     unwarran
    1.04
     tolerably
    1.04
     snoopy
    1.00
     ecru
    0.98
     maneu
    0.98
     paradiso
    0.96
     apprehen
    0.96
     madonna
    0.95
     disagre
    0.94
    Activations Density 1.076%

    No Known Activations