© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1533
    Prev
    Next
    INDEX
    Explanations

    chemical terms and symbols related to silver and nickel compounds and their properties

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

    Chemical formulas with numbers

    np_acts-logits-general · gemini-2.0-flash

    chemical elements and compounds

    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
     disambiguazione
    -0.67
     Administrativna
    -0.63
    Portale
    -0.48
     enfans
    -0.48
     tartalomajánló
    -0.47
    ReusableCell
    -0.45
    に進
    -0.44
    IsMutable
    -0.43
     bath
    -0.42
    rungsseite
    -0.42
    POSITIVE LOGITS
     referrerpolicy
    0.41
     Subsequently
    0.39
     Superhosts
    0.39
     muualla
    0.38
    creativecommons
    0.37
    offsetY
    0.37
     Nevertheless
    0.36
    <sup>
    0.36
     jadx
    0.36
     defStyleAttr
    0.35
    Activations Density 2.032%

    No Known Activations