© 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. 7670
    Prev
    Next
    INDEX
    Explanations

    details and descriptions of cricket matches

    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
    184
    +0.33
    1.3%
    964
    +0.27
    1.0%
    764
    +0.19
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.33
    0.01
    612
    +0.27
    0.00
    964
    +0.19
    0.01
    Negative Logits
     maroc
    -0.89
     embodi
    -0.86
     |]
    -0.82
     seclu
    -0.80
    arture
    -0.78
     uniqu
    -0.76
    lessed
    -0.76
    basti
    -0.75
    tuy
    -0.74
     indestru
    -0.73
    POSITIVE LOGITS
    InjectAttribute
    0.64
    dafx
    0.53
    .='
    0.53
    ValueStyle
    0.53
    ביוגרפיה
    0.52
     ModelExpression
    0.51
    archiviato
    0.50
    SEGUIR
    0.50
    astéro
    0.50
    <?
    0.49
    Activations Density 0.013%

    No Known Activations