© 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. 24-GEMMASCOPE-RES-16K
    11. 1383
    Prev
    Next
    INDEX
    Explanations

    nouns and verbs related to sharing and participation

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

    Following certain punctuation

    np_acts-logits-general · gemini-2.0-flash

    suggestions and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.42
     Normdatei
    -0.42
    WriteTagHelper
    -0.40
     Zähne
    -0.37
     kän
    -0.37
    ároz
    -0.36
     críticos
    -0.35
     Kindheit
    -0.35
     kecelakaan
    -0.35
    errHandler
    -0.35
    POSITIVE LOGITS
     visits
    0.56
     visit
    0.54
    visiting
    0.51
     searches
    0.51
     visiting
    0.51
     hunt
    0.50
     Commands
    0.50
    DispatchToProps
    0.49
     visited
    0.49
     Meksiku
    0.49
    Activations Density 0.765%

    No Known Activations