© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3679
    Prev
    Next
    INDEX
    Explanations

    text related to causality and common causes

    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
    468
    +0.15
    0.4%
    1842
    +0.12
    0.4%
    1967
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.15
    0.06
    1967
    +0.12
    0.05
    691
    +0.08
    0.01
    Negative Logits
     reluct
    -1.87
     intersper
    -1.73
     maneu
    -1.68
     apprehen
    -1.67
     disagre
    -1.66
     depic
    -1.63
     inev
    -1.62
     shenan
    -1.60
     unspeak
    -1.55
     accla
    -1.54
    POSITIVE LOGITS
    <bos>
    1.34
     something
    0.67
     oder
    0.59
    something
    0.58
    <?
    0.58
    Something
    0.57
    奈川
    0.56
    torie
    0.56
    某
    0.55
     thing
    0.55
    Activations Density 1.022%

    No Known Activations