© 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. 12916
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and rulings, especially those involving higher courts like the Supreme Court

    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
    78
    +0.10
    0.3%
    1557
    +0.10
    0.3%
    420
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    420
    +0.10
    0.02
    1557
    +0.10
    0.02
    376
    +0.10
    0.02
    Negative Logits
     unlaw
    -1.23
     disreg
    -1.18
     disagre
    -1.14
     shenan
    -1.14
     nutella
    -1.13
     reluct
    -1.11
     impra
    -1.10
     cushi
    -1.10
     apprehen
    -1.07
     encomp
    -1.05
    POSITIVE LOGITS
     Supreme
    1.35
    Supreme
    1.24
    supreme
    0.94
     supreme
    0.92
     SUPREME
    0.79
     Suprema
    0.74
     suprema
    0.66
     Supremo
    0.63
     Sup
    0.62
    cipar
    0.61
    Activations Density 0.051%

    No Known Activations