© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9517
    Prev
    Next
    INDEX
    Explanations

    elements related to data structure definitions and their properties

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

    numerical and type constraint keywords in structured data schemas and mathematical expressions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.58
    GOTREF
    -0.54
     disponibilités
    -0.52
    UnknownFieldSet
    -0.50
     kasarigan
    -0.43
    AnchorStyles
    -0.43
    ItemBackground
    -0.41
    verwijspagina
    -0.39
    hyrchwyd
    -0.39
    principalTable
    -0.39
    POSITIVE LOGITS
     integer
    1.72
     integers
    1.66
     Integer
    1.59
    Integer
    1.49
     numbers
    1.45
    integer
    1.39
    整数
    1.28
    integers
    1.27
     int
    1.24
     INTEGER
    1.24
    Activations Density 1.442%

    No Known Activations