© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 863
    Prev
    Next
    INDEX
    Explanations

    information related to law enforcement activities and investigations

    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
    +0.12
    0.3%
    946
    +0.12
    0.3%
    1499
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.12
    0.05
    1499
    +0.12
    0.06
    1048
    +0.09
    0.03
    Negative Logits
     increa
    -1.81
     swarovski
    -1.76
     impra
    -1.75
     oleo
    -1.73
     disagre
    -1.73
     affor
    -1.68
     reluct
    -1.68
     hairc
    -1.67
     guarante
    -1.66
     indestru
    -1.64
    POSITIVE LOGITS
     investigation
    0.75
     investigations
    0.62
     investigate
    0.62
     contact
    0.60
     архивлан
    0.59
    investigation
    0.58
     investigating
    0.58
    <bos>
    0.57
     review
    0.56
     contacted
    0.56
    Activations Density 0.384%

    No Known Activations