© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104708
    Prev
    Next
    INDEX
    Explanations

    the beginning of new sections or topics in text format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    LookAnd
    -0.50
    archiviato
    -0.49
    intenant
    -0.45
    دانشنامهٔ
    -0.42
     edisi
    -0.41
    nehå
    -0.39
    AsUp
    -0.39
    éndolo
    -0.39
     répondit
    -0.38
    alignSelf
    -0.38
    POSITIVE LOGITS
    NameInMap
    0.63
     noDo
    0.62
    Autoritní
    0.62
    KommentareTeilen
    0.59
    enumi
    0.55
    parametrize
    0.54
     transfieras
    0.54
    }));
    
    0.54
    Abit
    0.51
    enumii
    0.51
    Activations Density 0.032%

    No Known Activations