© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 37974
    Prev
    Next
    INDEX
    Explanations

    references to various types of cameras and film in the context of photography

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

    photography and film

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ableness
    -0.45
    ventil
    -0.42
    뀐
    -0.40
     utterance
    -0.39
     albero
    -0.39
    usammen
    -0.39
     flèche
    -0.36
     speaker
    -0.36
     normalized
    -0.35
    setHorizontal
    -0.35
    POSITIVE LOGITS
    XtraReports
    0.60
    ifilm
    0.58
     photographic
    0.57
     Polaroid
    0.56
     fotografico
    0.54
    fjspx
    0.52
     Kodak
    0.51
    tinyos
    0.50
     photographers
    0.50
     photographer
    0.50
    Activations Density 0.025%

    No Known Activations