Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 11032
    Prev
    Next
    INDEX
    Explanations

    file paths and directory navigation commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    —
    -0.57
    |}
    -0.56
    </h1>
    -0.56
     —
    -0.54
    }^{*
    -0.53
     Act
    -0.53
    on
    -0.53
    UIAlert
    -0.51
     igr
    -0.51
     lugar
    -0.50
    POSITIVE LOGITS
    ('./
    1.77
     ['./
    1.76
    ="./
    1.74
    ("./
    1.62
     './
    1.49
     ./
    1.43
    ../
    1.39
    './
    1.33
    ../../
    1.28
    ('../
    1.28
    Activations Density 0.107%

    No Known Activations