Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 822
    Prev
    Next
    INDEX
    Explanations

    function calls and return statements in code

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

    Code snippets or foreign language words

    np_acts-logits-general · gemini-2.0-flash

    closing parenthesis ) or ;

    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
    LabelTagHelper
    -0.72
    ValueStyle
    -0.69
     nakalista
    -0.67
    AddTagHelper
    -0.66
    Personensuche
    -0.65
     censiti
    -0.58
    ]")]
    -0.57
     AssemblyCompany
    -0.57
    SpringRunner
    -0.56
    IBOutlet
    -0.55
    POSITIVE LOGITS
     sitten
    0.47
     hasilnya
    0.43
     navideña
    0.43
     Inscrivez
    0.42
     takip
    0.39
     výsled
    0.39
     suivie
    0.38
    then
    0.37
     eredmény
    0.37
    bruik
    0.36
    Activations Density 0.372%

    No Known Activations