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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13-GEMMASCOPE-RES-16K
    6. 10136
    Prev
    Next
    INDEX
    Explanations

    sophisticated terminology related to argumentation and logical reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/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.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IE
    -0.41
    hies
    -0.41
    ‚¬
    -0.39
     volume
    -0.38
    nière
    -0.37
    róż
    -0.36
     Li
    -0.36
    scheme
    -0.36
    сма
    -0.36
    хал
    -0.35
    POSITIVE LOGITS
    ChildScrollView
    0.94
    #+#
    0.92
     GenerationType
    0.91
    InputBorder
    0.88
     виправивши
    0.86
     HasFactory
    0.85
    MessageOf
    0.83
    AutoScaleMode
    0.83
    +#+#
    0.81
     صوتيه
    0.78
    Activations Density 0.945%

    No Known Activations