Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1190
    Prev
    Next
    INDEX
    Explanations

    expressions of enthusiasm and personal connection towards hobbies or interests

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

    Following words related to hobbies or interests

    np_acts-logits-general · gemini-2.0-flash

    fondness for activities

    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
    IntoConstraints
    -0.47
     становника
    -0.44
    intenant
    -0.44
     raiſ
    -0.44
    vician
    -0.43
    tanleria
    -0.42
     Akismet
    -0.42
     kooper
    -0.42
    Tasting
    -0.41
     royaltyfri
    -0.40
    POSITIVE LOGITS
     love
    0.65
     encantan
    0.65
     fondness
    0.63
     gustan
    0.61
     loves
    0.59
     preferring
    0.56
    love
    0.56
     avid
    0.56
     favorite
    0.55
    ชอบ
    0.55
    Activations Density 0.260%

    No Known Activations