© 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. 28-GEMMASCOPE-RES-16K
    6. 4478
    Prev
    Next
    INDEX
    Explanations

    references to specific objects or entities involved in processes or functions

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

    after specific terms/variables

    np_acts-logits-general · gemini-2.0-flash

    prepositions of direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ниципа
    -0.40
    berday
    -0.39
    ocellular
    -0.38
    問題は
    -0.38
    nextDouble
    -0.38
    量は
    -0.37
    WebControls
    -0.37
    nonumber
    -0.36
     INTERPRET
    -0.36
     Exacts
    -0.35
    POSITIVE LOGITS
     into
    1.12
     onto
    1.03
     vào
    0.87
    into
    0.81
    Into
    0.73
     kepada
    0.72
     againſt
    0.66
     Into
    0.66
     unto
    0.64
     towards
    0.63
    Activations Density 2.076%

    No Known Activations