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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10667
    Prev
    Next
    INDEX
    Explanations

    Java programming constructs, particularly related to input/output operations and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.78
    ArgsConstructor
    -0.71
     iprot
    -0.65
    المشاركات
    -0.63
    SourceChecksum
    -0.56
    fromnode
    -0.55
    onActivityResult
    -0.55
     Trumb
    -0.53
    PostConstruct
    -0.53
     pancre
    -0.52
    POSITIVE LOGITS
    írus
    0.62
     وتسجيلات
    0.62
    ,:),
    0.58
    StoryboardSegue
    0.58
     disambiguazione
    0.55
    ňte
    0.51
    HORE
    0.51
    обходи
    0.51
     createSlice
    0.50
    apnews
    0.50
    Activations Density 0.029%

    No Known Activations