© 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. 13846
    Prev
    Next
    INDEX
    Explanations

    references to organizations, government programs, and legal terms

    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
    +0.14
    0.4%
    678
    +0.12
    0.4%
    1304
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1304
    +0.14
    0.05
    678
    +0.12
    0.04
    636
    +0.11
    0.04
    Negative Logits
    <bos>
    -0.93
     a
    -0.74
     (
    -0.73
     y
    -0.70
     int
    -0.69
     ten
    -0.68
     t
    -0.68
     а
    -0.67
     from
    -0.67
    相对
    -0.67
    POSITIVE LOGITS
     silikon
    2.15
     alkoh
    2.05
     kram
    2.05
     hcm
    2.05
     aen
    2.01
     dises
    1.99
     keramik
    1.98
     mef
    1.96
     meis
    1.95
     fta
    1.94
    Activations Density 0.143%

    No Known Activations