© 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. 40-GEMMASCOPE-RES-16K
    6. 1548
    Prev
    Next
    INDEX
    Explanations

    group gatherings and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.46
    ArrowToggle
    -0.45
    ########.
    -0.44
     Verfasser
    -0.43
     braços
    -0.42
     Vikipedi
    -0.42
    glLoadIdentity
    -0.42
    glPushMatrix
    -0.42
    LookAnd
    -0.41
    migrationBuilder
    -0.41
    POSITIVE LOGITS
     podcast
    1.72
     Podcast
    1.52
     listeners
    1.50
     episode
    1.49
    podcast
    1.46
     listener
    1.42
    Podcast
    1.41
     podcasts
    1.41
     Episode
    1.38
     episodes
    1.33
    Activations Density 0.215%

    No Known Activations