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. 31-GEMMASCOPE-RES-16K
    6. 3303
    Prev
    Next
    INDEX
    Explanations

    references to specific film categories and attributes, such as genre and language

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

    Wikipedia article metadata and categorical tags, particularly year numbers and film classification information.

    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
    protoimpl
    -0.54
    LabelTagHelper
    -0.51
     Infórmanos
    -0.48
     gyvento
    -0.47
    ########.
    -0.47
     atlik
    -0.45
    Personendaten
    -0.45
     ilustracji
    -0.44
    ($__
    -0.44
    MigrationBuilder
    -0.43
    POSITIVE LOGITS
     blockbuster
    0.93
     thriller
    0.92
     film
    0.85
     movie
    0.81
     films
    0.79
     sci
    0.77
     movies
    0.76
     flick
    0.73
     comedy
    0.72
     horror
    0.72
    Activations Density 0.298%

    No Known Activations