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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3101
    Prev
    Next
    INDEX
    Explanations

    names and identities of individuals discussed in relation to achievements or events

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

    Names followed by verbs or numbers

    np_acts-logits-general · gemini-2.0-flash

    pronouns and names followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.62
     <>",
    -0.56
    曖昧さ回避
    -0.50
    StoryboardSegue
    -0.50
    IntoConstraints
    -0.50
     CascadeType
    -0.49
    HtmlAttribute
    -0.48
    arraycopy
    -0.47
     تضيفلها
    -0.46
     ObjectParameter
    -0.46
    POSITIVE LOGITS
    Życiorys
    0.47
     totalidad
    0.36
    IZONTAL
    0.35
     famously
    0.35
    AutoModerator
    0.34
    OPINION
    0.34
     maisha
    0.34
     Regierung
    0.33
    |(
    0.32
    äldrar
    0.32
    Activations Density 0.385%

    No Known Activations