© 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. 7680
    Prev
    Next
    INDEX
    Explanations

    questions and conversation prompts

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

    Follows square brackets

    np_acts-logits-general · gemini-2.0-flash

    asking for descriptions

    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
     rhestr
    -0.62
     Houſe
    -0.61
    onedDateTime
    -0.57
     newBuilder
    -0.56
     estekak
    -0.54
    bootstrapcdn
    -0.54
    TagMode
    -0.53
    tagHelperRunner
    -0.53
    SequentialGroup
    -0.52
    Xna
    -0.52
    POSITIVE LOGITS
    How
    0.49
    Regarding
    0.49
    Does
    0.47
    describe
    0.43
    Could
    0.42
    Are
    0.42
    When
    0.42
    föra
    0.41
    Describe
    0.41
     describir
    0.41
    Activations Density 0.123%

    No Known Activations