© 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. 7597
    Prev
    Next
    INDEX
    Explanations

    quotations or phrases enclosed in single quotes

    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
    1034
    +0.17
    0.6%
    528
    +0.15
    0.5%
    2011
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1034
    +0.17
    0.05
    1404
    +0.15
    0.05
    303
    +0.14
    0.04
    Negative Logits
    <eos>
    -0.73
     bat
    -0.51
     SOL
    -0.45
    рисов
    -0.45
    ,
    -0.44
    crochet
    -0.44
     lamp
    -0.44
     lat
    -0.44
     Bat
    -0.43
     signal
    -0.42
    POSITIVE LOGITS
     inol
    0.85
     vogli
    0.81
     magis
    0.79
     voleva
    0.76
     corris
    0.76
     potest
    0.75
     doveva
    0.75
     poichè
    0.74
     istan
    0.74
     meras
    0.73
    Activations Density 0.129%

    No Known Activations