© 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. 3526
    Prev
    Next
    INDEX
    Explanations

    specific historical dates

    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
    1978
    +0.16
    0.5%
    776
    +0.15
    0.5%
    1741
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.16
    0.04
    1141
    +0.15
    0.03
    776
    +0.11
    0.04
    Negative Logits
    <bos>
    -0.73
     (
    -0.63
     to
    -0.61
     in
    -0.60
    ,
    -0.60
     at
    -0.60
    .
    -0.59
     as
    -0.59
     so
    -0.59
     that
    -0.58
    POSITIVE LOGITS
     silikon
    1.69
     alkoh
    1.68
     antik
    1.68
     makro
    1.64
     kram
    1.61
     ekos
    1.61
     keramik
    1.57
     uhr
    1.55
     optik
    1.52
     karton
    1.52
    Activations Density 0.051%

    No Known Activations