Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15336
    Prev
    Next
    INDEX
    Explanations

    references to firearms, gun violence, and related policies or discussions

    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
    479
    +0.15
    0.6%
    1296
    +0.14
    0.5%
    1837
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.15
    0.05
    1296
    +0.14
    0.04
    1837
    +0.11
    0.04
    Negative Logits
     intermitt
    -0.64
     stanley
    -0.61
     reluct
    -0.61
     reconno
    -0.61
     suscep
    -0.60
     fischer
    -0.60
     krab
    -0.58
     disreg
    -0.58
     ert
    -0.58
     rita
    -0.58
    POSITIVE LOGITS
     gun
    1.40
     Gun
    1.31
     guns
    1.29
    Gun
    1.28
    gun
    1.23
     GUN
    1.16
    Guns
    1.15
     Guns
    1.10
    guns
    1.09
    GUN
    1.07
    Activations Density 0.088%

    No Known Activations