© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12930
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters

    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
    +0.16
    0.5%
    442
    +0.09
    0.3%
    892
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.16
    0.02
    204
    +0.09
    0.01
    1623
    +0.08
    0.02
    Negative Logits
    ,
    -0.58
    .
    -0.56
    -
    -0.55
    Tikang
    -0.54
     of
    -0.53
     to
    -0.52
     in
    -0.51
     and
    -0.51
     y
    -0.50
     w
    -0.50
    POSITIVE LOGITS
     parteci
    1.21
     ciasc
    1.13
     sappi
    1.09
     Luglio
    1.07
     🤣🤣
    1.07
     soggior
    1.06
    ☺☺
    1.06
     prega
    1.06
     venerdì
    1.05
     ?...
    1.04
    Activations Density 0.044%

    No Known Activations