© 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. 14-GEMMASCOPE-RES-16K
    11. 4428
    Prev
    Next
    INDEX
    Explanations

    statements of admission or acknowledgment of past actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dra
    -0.73
     Thomas
    -0.66
    :+:
    -0.65
    Dra
    -0.64
    XmlType
    -0.64
    ený
    -0.63
    overrightarrow
    -0.61
     dra
    -0.61
    ClientSize
    -0.61
    Continu
    -0.61
    POSITIVE LOGITS
     admit
    1.38
     Admit
    1.36
     admitted
    1.31
     admits
    1.30
     admitting
    1.27
     Admissions
    1.25
     admissions
    1.23
     confesses
    1.23
    Admissions
    1.16
     confess
    1.16
    Activations Density 0.131%

    No Known Activations