© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4516
    Prev
    Next
    INDEX
    Explanations

    elements related to names, titles, and notable achievements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    proper names and text-based references to publishing or media entities.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyVersion
    -0.45
     numerus
    -0.39
     OnDestroy
    -0.39
    Voltaje
    -0.39
    ErrUnexpectedEOF
    -0.38
     gyhoeddwyd
    -0.38
     面包
    -0.37
    getKeyCode
    -0.37
    endaftaran
    -0.36
    kozások
    -0.36
    POSITIVE LOGITS
    Personendaten
    0.54
    }}]{
    0.45
     lifestyles
    0.45
     Arad
    0.45
     OTO
    0.43
     screens
    0.43
    PROMOTED
    0.42
    ⁝
    0.42
    OOTDTY
    0.41
    KURZBESCHREIBUNG
    0.41
    Activations Density 0.067%

    No Known Activations