© 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. 17-GEMMASCOPE-RES-16K
    11. 10575
    Prev
    Next
    INDEX
    Explanations

    key words and phrases related to confirmation and validation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ிறது
    -0.61
     venuto
    -0.60
    vajú
    -0.59
    actéristique
    -0.57
     contained
    -0.57
     resultó
    -0.55
     ⓒ
    -0.54
    ίνει
    -0.54
    >>>>>>>
    -0.53
    ajú
    -0.52
    POSITIVE LOGITS
     you
    0.91
     we
    0.82
     I
    0.61
    you
    0.54
     ModelExpression
    0.53
     noDo
    0.52
     yourself
    0.50
    celotti
    0.50
    ikita
    0.49
     resourceCulture
    0.49
    Activations Density 0.070%

    No Known Activations