© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 11345
    Prev
    Next
    INDEX
    Explanations

    sentences expressing connections and relationships between people

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

    Referring to people or entities

    np_acts-logits-general · gemini-2.0-flash

    identifying people and relationships

    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
    AnchorStyles
    -0.49
     ModelExpression
    -0.47
    enterOuterAlt
    -0.46
     ProtoMessage
    -0.40
    цездатний
    -0.40
    MigrationBuilder
    -0.40
    XmlAccessorType
    -0.34
     snippetHide
    -0.34
    WithMany
    -0.34
     sink
    -0.33
    POSITIVE LOGITS
     whom
    0.69
    whom
    0.64
    Whom
    0.60
     Whom
    0.56
     whome
    0.55
    ManyToOne
    0.54
    StoryboardSegue
    0.54
     кого
    0.53
     kekasih
    0.52
     enemy
    0.52
    Activations Density 1.004%

    No Known Activations