© 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. 13922
    Prev
    Next
    INDEX
    Explanations

    terms related to societal issues, including minority groups, inequality, and social justice movements

    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
    198
    +0.15
    0.4%
    1842
    +0.13
    0.4%
    856
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.15
    0.06
    1510
    +0.13
    0.04
    1202
    +0.09
    0.03
    Negative Logits
    <bos>
    -0.86
    RTSC
    -0.66
    FormTagHelper
    -0.63
    LabelTagHelper
    -0.61
    styleUrls
    -0.61
    Palmar
    -0.61
    setDo
    -0.60
    CodedInputStream
    -0.60
    Manbalar
    -0.57
     Wiktionnaire
    -0.57
    POSITIVE LOGITS
     increa
    1.40
     affor
    1.37
     guarante
    1.37
     encomp
    1.34
     shenan
    1.34
     apprehen
    1.32
     strick
    1.30
     intersper
    1.30
     gaily
    1.30
     scrat
    1.29
    Activations Density 0.353%

    No Known Activations