© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4711
    Prev
    Next
    INDEX
    Explanations

    Java annotations and configuration details within code

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

    Java-related code or annotations

    np_acts-logits-general · gemini-2.0-flash

    an mitochondrial management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    IUrlHelper
    -0.86
    Rhestr
    -0.75
    ViewFeatures
    -0.67
    rungsseite
    -0.63
    LookAnd
    -0.61
    ffilm
    -0.58
    seamnă
    -0.56
     препратки
    -0.55
    optarg
    -0.55
    ταν
    -0.54
    POSITIVE LOGITS
    public
    0.65
     public
    0.52
    帖最后由
    0.51
     فريبيس
    0.47
     referrerpolicy
    0.47
     class
    0.47
    ranean
    0.46
    ContentAsync
    0.46
    classes
    0.46
     classes
    0.45
    Activations Density 0.070%

    No Known Activations