© 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. 17-GEMMASCOPE-RES-16K
    6. 12998
    Prev
    Next
    INDEX
    Explanations

    the definite article "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.92
    Personendaten
    -0.82
     Chwiliwch
    -0.80
    +#+#
    -0.79
    клопе
    -0.77
    ScopeManager
    -0.77
    AccessorTable
    -0.76
    explique
    -0.75
     oprot
    -0.75
    berdayakan
    -0.73
    POSITIVE LOGITS
    <bos>
    0.78
    '
    0.63
    ’
    0.49
     
    0.47
     former
    0.44
     tqdm
    0.44
    1
    0.42
    घ
    0.42
     milieu
    0.41
     }_{
    0.41
    Activations Density 0.253%

    No Known Activations