© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 1962
    Prev
    Next
    INDEX
    Explanations

    numerical values and their associations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -1.09
     CreateTagHelper
    -1.08
     autorytatywna
    -1.05
    protoimpl
    -1.03
    GEBURTSDATUM
    -0.96
    rungsseite
    -0.93
     وتسجيلات
    -0.93
     الحره
    -0.92
    LookAnd
    -0.90
    QMetaType
    -0.89
    POSITIVE LOGITS
    REDIRECT
    0.49
    wetter
    0.42
     by
    0.42
    ...
    0.41
     even
    0.41
    skapet
    0.41
    jande
    0.40
     von
    0.40
     terbesar
    0.39
     едино
    0.39
    Activations Density 1.166%

    No Known Activations