© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13871
    Prev
    Next
    INDEX
    Explanations

    sentences containing narratives about people or events

    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
    1577
    +0.26
    0.9%
    394
    +0.22
    0.8%
    674
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.26
    0.02
    1531
    +0.22
    0.08
    16
    +0.17
    0.17
    Negative Logits
     reluct
    -1.52
     apprehen
    -1.44
     gaily
    -1.43
     disagre
    -1.43
     shenan
    -1.41
     withal
    -1.39
     intersper
    -1.37
     unspeak
    -1.37
     encomp
    -1.34
     strick
    -1.29
    POSITIVE LOGITS
    <bos>
    1.09
    Citiți
    0.75
    ↘
    0.68
    ↗
    0.65
    Alguna
    0.63
    Și
    0.62
    Identyfik
    0.61
     lenker
    0.60
    Pentru
    0.60
    Autoritní
    0.60
    Activations Density 5.859%

    No Known Activations