© 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. 14545
    Prev
    Next
    INDEX
    Explanations

    contractions containing apostrophes indicating omitted letters

    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
    478
    +0.17
    0.5%
    1699
    +0.14
    0.4%
    394
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.17
    0.13
    1533
    +0.14
    0.09
    610
    +0.13
    0.13
    Negative Logits
     hentai
    -0.91
     shenan
    -0.90
     maneu
    -0.86
     hairc
    -0.83
     rascal
    -0.82
     motherfucker
    -0.82
     dumbass
    -0.82
    Lma
    -0.81
    Cringe
    -0.77
     intersper
    -0.76
    POSITIVE LOGITS
     torba
    1.10
    (%)
    1.00
     silikon
    1.00
     valla
    1.00
     kafe
    0.94
     pól
    0.94
     alkoh
    0.93
     vasi
    0.93
     parati
    0.92
     palio
    0.91
    Activations Density 0.943%

    No Known Activations