© 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. 27-GEMMASCOPE-RES-16K
    6. 9389
    Prev
    Next
    INDEX
    Explanations

    keywords associated with programming concepts, particularly in coding or data structure contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.76
    ]")]
    -0.74
     AssemblyCompany
    -0.73
    EDEFAULT
    -0.71
    complexContent
    -0.70
    PropertyChanging
    -0.69
     AssemblyVersion
    -0.67
    LookAnd
    -0.66
    TypedDataSet
    -0.64
     AssemblyTitle
    -0.63
    POSITIVE LOGITS
     node
    0.53
     nodes
    0.42
     tag
    0.39
     parse
    0.38
     syntax
    0.38
    node
    0.37
     parsing
    0.37
    Parsing
    0.37
     grammatical
    0.35
     buscas
    0.35
    Activations Density 0.781%

    No Known Activations