© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 2010
    Prev
    Next
    INDEX
    Explanations

    code constructs related to data operations and processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Phono
    -0.82
     ſtate
    -0.80
     Morality
    -0.80
     Polity
    -0.79
     Resin
    -0.79
     Marrow
    -0.78
     NDEBUG
    -0.78
     Pesto
    -0.78
     Cognition
    -0.77
     Topology
    -0.77
    POSITIVE LOGITS
     that
    0.86
     if
    0.84
     which
    0.82
     You
    0.81
     They
    0.81
     a
    0.80
     That
    0.80
     If
    0.80
     the
    0.80
     with
    0.79
    Activations Density 1.796%

    No Known Activations