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. 14-GEMMASCOPE-RES-16K
    6. 10363
    Prev
    Next
    INDEX
    Explanations

    calls to action and urgency in persuasive texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sätzlich
    -0.57
    supset
    -0.53
    んだり
    -0.48
     ogóle
    -0.47
     mesmas
    -0.43
    ủi
    -0.43
    HttpPut
    -0.43
    abcdefghijklmnop
    -0.42
     gelernt
    -0.41
    uría
    -0.41
    POSITIVE LOGITS
     الحره
    0.76
    EndInit
    0.72
    migrationBuilder
    0.70
    ArgsConstructor
    0.69
    PreferredItem
    0.67
     Hurry
    0.67
    setViewportView
    0.65
     hurry
    0.65
     ExecuteAsync
    0.65
    ChildScrollView
    0.62
    Activations Density 0.127%

    No Known Activations