© 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. 2479
    Prev
    Next
    INDEX
    Explanations

    references to political events, government actions, and international relations

    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
    376
    +0.08
    0.2%
    1323
    +0.08
    0.2%
    1096
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    315
    +0.08
    0.04
    362
    +0.08
    0.04
    402
    +0.08
    0.04
    Negative Logits
     חיצוניים
    -0.54
    )}$,
    -0.49
    WithIdentifier
    -0.48
    RegressionTest
    -0.48
    __':
    -0.48
    )}$.
    -0.48
    >);
    -0.47
     \%-
    -0.46
     \%$.
    -0.46
    ITE
    -0.45
    POSITIVE LOGITS
     squa
    1.02
     dises
    1.02
     igno
    0.97
     fta
    0.95
     fep
    0.95
     unce
    0.94
     encomp
    0.94
     aen
    0.94
     chande
    0.93
     increa
    0.93
    Activations Density 0.136%

    No Known Activations