© 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. 13897
    Prev
    Next
    INDEX
    Explanations

    statements of criticism or commentary towards public figures or social 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
    453
    +0.17
    0.5%
    1343
    +0.14
    0.4%
    1978
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.17
    0.03
    1803
    +0.14
    0.03
    1135
    +0.14
    0.02
    Negative Logits
     unspeak
    -1.84
     intersper
    -1.83
     increa
    -1.83
     snoopy
    -1.80
     fta
    -1.79
     thut
    -1.78
     ftu
    -1.78
     tolerably
    -1.75
     gaily
    -1.74
     apprehen
    -1.72
    POSITIVE LOGITS
    FlatAppearance
    0.86
    IntoConstraints
    0.72
    NOPQRST
    0.71
    DataPropertyName
    0.70
    Tē
    0.67
    Producción
    0.67
    Opere
    0.67
    FlatStyle
    0.67
    dymyr
    0.66
    imageio
    0.65
    Activations Density 0.030%

    No Known Activations