© 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. 13771
    Prev
    Next
    INDEX
    Explanations

    structured information like codes, numbers, and formats

    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
    674
    +0.12
    0.4%
    1978
    +0.10
    0.3%
    1343
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.12
    0.05
    453
    +0.10
    0.04
    1107
    +0.10
    0.03
    Negative Logits
     implacable
    -0.79
     exasper
    -0.79
     pamph
    -0.79
     Punj
    -0.73
     tolerably
    -0.73
     unspeak
    -0.73
     intrigu
    -0.72
     inconce
    -0.71
     luxuriant
    -0.70
     rancho
    -0.70
    POSITIVE LOGITS
    0
    0.70
    webElementXpaths
    0.52
    ০
    0.48
     \\
    0.43
     insegu
    0.42
     RECRE
    0.42
     medes
    0.41
    ０
    0.41
    NSIndexPath
    0.41
     frenos
    0.41
    Activations Density 0.157%

    No Known Activations