© 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. 31-GEMMASCOPE-RES-16K
    6. 8833
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue or statements from individuals

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

    pronouns followed by verbs of speech or action (like "he said," "she added," "they continued").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.56
     BorderSide
    -0.44
     considérons
    -0.43
     jsPsych
    -0.43
    reaction
    -0.41
    jmniej
    -0.40
     détach
    -0.40
    LabelTagHelper
    -0.40
    colhead
    -0.39
    JvmStatic
    -0.39
    POSITIVE LOGITS
     added
    1.46
     further
    1.45
    further
    1.23
     adds
    1.17
     continued
    1.08
     weiter
    1.07
     agregó
    1.07
     Added
    1.06
    Added
    1.05
     añadió
    1.05
    Activations Density 0.245%

    No Known Activations