© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1933
    Prev
    Next
    INDEX
    Explanations

    numeric values listed in a specific format

    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
    +0.10
    0.3%
    266
    +0.10
    0.3%
    86
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    975
    +0.10
    0.02
    609
    +0.10
    0.03
    523
    +0.08
    0.02
    Negative Logits
     unwarran
    -0.94
     apprehen
    -0.80
     disagre
    -0.78
     maneu
    -0.77
     pamph
    -0.75
     homeward
    -0.75
     impractica
    -0.75
     gaily
    -0.74
     reluct
    -0.74
     snoopy
    -0.70
    POSITIVE LOGITS
    WebElementEntity
    0.54
    ButtonModule
    0.46
    pense
    0.45
     getItemId
    0.44
     pañ
    0.43
    rítica
    0.43
    getIntent
    0.43
     grammi
    0.42
     ums
    0.42
    lumb
    0.42
    Activations Density 0.184%

    No Known Activations