© 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. 20-GEMMASCOPE-RES-16K
    11. 5500
    Prev
    Next
    INDEX
    Explanations

    elements and structures related to programming and data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Type" or its variants, often followed by a method call

    np_acts-logits-general · gemini-2.0-flash

    type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Handlung
    -0.51
    Coordonnées
    -0.44
     bỏ
    -0.43
    ExecutionContext
    -0.43
    SessionId
    -0.43
     stimm
    -0.42
    NegativeButton
    -0.42
    Naissance
    -0.42
     Nunn
    -0.42
    ẵ
    -0.41
    POSITIVE LOGITS
     type
    2.72
    type
    2.41
     Type
    2.39
     TYPE
    2.31
    Type
    2.30
     types
    2.24
    TYPE
    2.11
    getType
    2.06
     getType
    2.04
     tipo
    2.02
    Activations Density 0.335%

    No Known Activations