© 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. 10-GEMMASCOPE-RES-16K
    6. 1828
    Prev
    Next
    INDEX
    Explanations

    elements associated with JSON parsing and handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.72
    MLLoader
    -0.67
    PhysRevD
    -0.64
     HomeComponent
    -0.60
    Enllaces
    -0.56
    __":
    -0.56
    astéroïdes
    -0.56
    __':
    -0.56
    KURZBESCHREIBUNG
    -0.56
    ArgsConstructor
    -0.55
    POSITIVE LOGITS
    ledning
    0.56
    NSDictionary
    0.51
    XMLSchema
    0.49
    iare
    0.47
     (!_
    0.46
    tifact
    0.46
     cref
    0.45
    ernalia
    0.45
     Aprend
    0.44
    Crime
    0.44
    Activations Density 0.113%

    No Known Activations