© 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. 2-GEMMASCOPE-RES-16K
    11. 4118
    Prev
    Next
    INDEX
    Explanations

    terms related to software development and programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    хьтан
    -0.35
    AccessorTable
    -0.30
    awaiter
    -0.30
    tschafts
    -0.28
    ussure
    -0.25
    อ
    -0.24
    faßt
    -0.23
    Eksterne
    -0.23
    তথ্যসূত্র
    -0.23
    นน
    -0.22
    POSITIVE LOGITS
    ging
    1.41
    gie
    1.35
    gas
    1.34
    gers
    1.33
    gs
    1.33
    gies
    1.31
    ged
    1.31
    gos
    1.28
    gon
    1.26
    gar
    1.23
    Activations Density 0.667%

    No Known Activations