© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 4690
    Prev
    Next
    INDEX
    Explanations

    expressions related to variable assignment and comparison in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mergeFrom
    -0.67
    ">—
    -0.63
    nothing
    -0.53
    
    -0.53
     nada
    -0.52
    <bos>
    -0.50
    several
    -0.49
    ReusableCell
    -0.49
    zero
    -0.49
     zero
    -0.49
    POSITIVE LOGITS
     true
    2.50
    true
    2.31
    True
    1.66
     True
    1.64
     TRUE
    1.64
    TRUE
    1.53
     verdadeiro
    1.44
     verdadero
    1.40
     vrai
    1.40
     verdadera
    1.36
    Activations Density 0.065%

    No Known Activations