© 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. 3530
    Prev
    Next
    INDEX
    Explanations

    names of technological components and settings

    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
    381
    +0.17
    0.6%
    1328
    +0.14
    0.5%
    1978
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1328
    +0.17
    0.05
    130
    +0.14
    0.06
    678
    +0.10
    0.06
    Negative Logits
     sii
    -1.11
     ghe
    -1.02
     fte
    -1.01
     lii
    -1.00
     tew
    -0.99
     goi
    -0.96
     nant
    -0.95
     drey
    -0.95
     afo
    -0.93
     „,
    -0.93
    POSITIVE LOGITS
     quoique
    0.82
     Pourtant
    0.78
     Voyez
    0.78
     dégust
    0.75
     quelquefois
    0.72
     exé
    0.70
    Fitment
    0.70
     Maintenant
    0.69
     semblait
    0.69
     Ceux
    0.68
    Activations Density 0.440%

    No Known Activations