© 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. 13938
    Prev
    Next
    INDEX
    Explanations

    statements highlighting societal or political issues

    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
    1741
    +0.17
    0.6%
    2019
    +0.11
    0.4%
    1967
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    781
    +0.17
    0.04
    468
    +0.11
    0.04
    47
    +0.11
    0.04
    Negative Logits
     maksi
    -1.02
     Abbé
    -0.98
     tramonto
    -0.92
     Shakspeare
    -0.91
     Cæsar
    -0.87
     Eccle
    -0.87
     Mémoires
    -0.86
     saar
    -0.86
     alip
    -0.86
     strick
    -0.85
    POSITIVE LOGITS
     same
    0.88
     reason
    0.78
     biggest
    0.73
     easiest
    0.72
     exact
    0.70
    same
    0.69
     result
    0.69
     largest
    0.66
     best
    0.66
     way
    0.66
    Activations Density 0.230%

    No Known Activations