© 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. 2354
    Prev
    Next
    INDEX
    Explanations

    information or statistics from research studies

    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
    690
    +0.11
    0.3%
    1370
    +0.11
    0.3%
    1253
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1370
    +0.11
    0.05
    559
    +0.11
    0.04
    1430
    +0.09
    0.04
    Negative Logits
     reconnaît
    -0.75
     occupe
    -0.73
     saurait
    -0.72
     nomme
    -0.71
     ecclesias
    -0.71
     viciss
    -0.70
     disait
    -0.70
     eiffel
    -0.69
     défend
    -0.69
     vespa
    -0.68
    POSITIVE LOGITS
    BeginInit
    0.66
     findings
    0.64
     defStyle
    0.62
     that
    0.58
     buhay
    0.58
     found
    0.56
    ContentAsync
    0.56
    ochlor
    0.55
     febru
    0.55
     bawat
    0.55
    Activations Density 0.174%

    No Known Activations