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. 10-GEMMASCOPE-RES-16K
    6. 13164
    Prev
    Next
    INDEX
    Explanations

    monetary values and related symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -1.13
    ']")
    -0.88
     Paglinawan
    -0.80
    LLocation
    -0.76
    .');
    -0.76
    ')")
    -0.74
    Ecotoxicity
    -0.74
    LookAnd
    -0.73
    تقاوى
    -0.73
    }');
    -0.71
    POSITIVE LOGITS
    <td>
    0.81
     yoksa
    0.58
    jfree
    0.57
    enumi
    0.56
    <th>
    0.55
    ['
    0.53
    substack
    0.52
     bırak
    0.52
    tså
    0.52
     Grig
    0.51
    Activations Density 0.098%

    No Known Activations