© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2713
    Prev
    Next
    INDEX
    Explanations

    technical references and commands related to programming environments or software installations

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

    file paths and directory structures in code and error messages.

    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
    Personendaten
    -0.48
     виправивши
    -0.41
     pulumi
    -0.41
     contact
    -0.39
    SourceChecksum
    -0.35
    routeProvider
    -0.35
     SPDX
    -0.34
    存于互联网档案馆
    -0.34
     DFA
    -0.33
    eseorang
    -0.32
    POSITIVE LOGITS
    enterian
    0.48
    installed
    0.46
    libft
    0.46
    vendor
    0.45
     superimposed
    0.44
    alyptus
    0.43
    share
    0.42
     frameworks
    0.42
    Huile
    0.42
    øk
    0.41
    Activations Density 0.476%

    No Known Activations