© 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. 13696
    Prev
    Next
    INDEX
    Explanations

    terms related to criminal activities and law enforcement

    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
    1870
    +0.15
    0.6%
    1416
    +0.12
    0.4%
    1994
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1994
    +0.15
    0.03
    1425
    +0.12
    0.03
    1416
    +0.11
    0.03
    Negative Logits
    Grüße
    -0.55
     suga
    -0.51
    Grath
    -0.50
     conges
    -0.48
     redhead
    -0.47
     motherfucker
    -0.47
     impotence
    -0.47
    throwaway
    -0.46
    AutoScaleMode
    -0.45
     pikachu
    -0.45
    POSITIVE LOGITS
     criminal
    1.24
    Criminal
    1.14
    criminal
    1.13
     Criminal
    1.11
     CRIMINAL
    0.94
     kriminal
    0.93
     Crim
    0.90
     criminals
    0.84
     crimin
    0.83
     Crimin
    0.75
    Activations Density 0.060%

    No Known Activations