© 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. 7701
    Prev
    Next
    INDEX
    Explanations

    technical details and specifications related to hardware and equipment

    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
    1438
    +0.11
    0.4%
    416
    +0.10
    0.3%
    1314
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.11
    0.06
    284
    +0.10
    0.07
    416
    +0.10
    0.06
    Negative Logits
     tramont
    -1.08
     fluo
    -1.07
     sappi
    -1.03
     nephe
    -0.98
     incess
    -0.95
     Settembre
    -0.92
     thermomix
    -0.92
     biex
    -0.92
     Luglio
    -0.92
     vogli
    -0.92
    POSITIVE LOGITS
    页面存档备份
    0.49
    GOTREF
    0.47
    isContained
    0.47
     afla
    0.46
     salvación
    0.45
     declarat
    0.45
    着丈
    0.45
     urme
    0.44
     fühlte
    0.43
     straight
    0.43
    Activations Density 0.715%

    No Known Activations