© 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. 0-GEMMASCOPE-RES-16K
    6. 2973
    Prev
    Next
    INDEX
    Explanations

    text related to references and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Innen
    -0.35
     mittlerweile
    -0.34
     Øst
    -0.34
     beraber
    -0.34
     resourceCulture
    -0.32
     kolejne
    -0.31
     dostępne
    -0.31
    erequisite
    -0.30
     cobr
    -0.30
     kommune
    -0.30
    POSITIVE LOGITS
    rec
    0.75
    Personendaten
    0.69
     rec
    0.66
     Rec
    0.65
    Rec
    0.64
    dis
    0.60
    conscious
    0.58
    RTCK
    0.58
     conscious
    0.57
    recs
    0.57
    Activations Density 0.305%

    No Known Activations