© 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. 979
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "shooting" along with related terms like "fire," "shot," and "sniper."

    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
    1942
    +0.15
    0.5%
    410
    +0.13
    0.5%
    971
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1942
    +0.15
    0.05
    1018
    +0.13
    0.04
    410
    +0.12
    0.04
    Negative Logits
     Pils
    -0.46
     Ains
    -0.46
     mait
    -0.43
     Perp
    -0.43
    Mav
    -0.42
     Menlo
    -0.42
     géné
    -0.42
    nemia
    -0.41
    Nei
    -0.41
     Youngstown
    -0.41
    POSITIVE LOGITS
     shooting
    1.38
     Shooting
    1.33
     shoot
    1.33
    shooting
    1.25
     Shoot
    1.25
    Shooting
    1.23
     shoots
    1.18
    Shoot
    1.15
    shoot
    1.14
     shootings
    1.13
    Activations Density 0.100%

    No Known Activations