© 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. 7705
    Prev
    Next
    INDEX
    Explanations

    phrases related to gaming mechanics and specifications

    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
    906
    +0.14
    0.4%
    1385
    +0.13
    0.4%
    1526
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1526
    +0.14
    0.05
    1283
    +0.13
    0.04
    766
    +0.10
    0.04
    Negative Logits
     Haci
    -0.50
     rouleau
    -0.46
     obé
    -0.45
     teto
    -0.45
     HasFactory
    -0.44
     Momb
    -0.44
     bâton
    -0.44
     équilibr
    -0.43
     exé
    -0.43
     éte
    -0.43
    POSITIVE LOGITS
     area
    0.87
     areas
    0.80
    area
    0.74
    areas
    0.73
    Area
    0.68
     AREAS
    0.65
     radius
    0.65
    Areas
    0.64
     AREA
    0.64
     Areas
    0.63
    Activations Density 0.519%

    No Known Activations