© 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. 3368
    Prev
    Next
    INDEX
    Explanations

    references to updates and maintenance of information or profiles

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

    instructions or directives to update, keep current, or maintain information.

    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
    TagMode
    -0.43
    HomeAsUpEnabled
    -0.40
    EDEFAULT
    -0.39
    новништво
    -0.36
    发明
    -0.35
    󠁴
    -0.35
     étrangère
    -0.34
    StoryboardSegue
    -0.32
     المعيارى
    -0.32
    mpions
    -0.31
    POSITIVE LOGITS
     update
    2.75
     updating
    2.47
     updates
    2.45
     Update
    2.39
     updated
    2.34
    update
    2.30
    更新
    2.23
     Updating
    2.19
    Update
    2.19
     Updates
    2.17
    Activations Density 0.398%

    No Known Activations