© 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. 24-GEMMASCOPE-RES-16K
    6. 5206
    Prev
    Next
    INDEX
    Explanations

    key components and syntax related to SQL queries and database operations

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

    Code, symbols, and unusual punctuation

    np_acts-logits-general · gemini-2.0-flash

    end of code or string

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.58
     AssemblyTitle
    -0.56
    InputTagHelper
    -0.53
     disambiguazione
    -0.49
    verwijspagina
    -0.49
     pinulongan
    -0.48
     beginnetje
    -0.48
     PeEnEo
    -0.48
    RTGC
    -0.47
    EditorBrowsable
    -0.47
    POSITIVE LOGITS
    enderror
    0.45
    SpringBootTest
    0.41
     ModelExpression
    0.40
     prochaines
    0.39
    PullParser
    0.38
    MathML
    0.37
    ceğine
    0.35
    tagens
    0.35
    ľov
    0.35
     deadline
    0.35
    Activations Density 0.200%

    No Known Activations