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. 18-GEMMASCOPE-RES-16K
    6. 14577
    Prev
    Next
    INDEX
    Explanations

    references to "hand" as a descriptor in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "hand" and its variations

    np_acts-logits-general · gemini-2.0-flash

    hand compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.73
    ByVersion
    -0.68
    StoryboardSegue
    -0.63
     initComponents
    -0.63
    CrossRef
    -0.61
    المناصب
    -0.59
    IBOutlet
    -0.59
    cshtml
    -0.58
    ContentAsync
    -0.58
    </thead>
    -0.55
    POSITIVE LOGITS
     HAND
    1.25
     Hand
    1.24
    Hand
    1.17
     hand
    1.16
    HAND
    1.15
     Hands
    1.12
    hand
    1.06
     hands
    0.98
    Hands
    0.96
     HANDS
    0.91
    Activations Density 0.099%

    No Known Activations