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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8090
    Prev
    Next
    INDEX
    Explanations

    function definitions and method parameters in code

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

    Code snippets or code-related syntax

    np_acts-logits-general · gemini-2.0-flash

    rectangular current

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.63
     nahilalakip
    -0.57
     Wikiseite
    -0.56
     elif
    -0.50
    expandindo
    -0.49
    出版年
    -0.48
    Cordialement
    -0.48
    copg
    -0.47
     محفوظة
    -0.47
     viewDidLoad
    -0.47
    POSITIVE LOGITS
    ↵
    0.98
    ↵↵
    0.47
    ↵↵↵
    0.45
    </i>
    0.44
     }}"
    0.42
    </em>
    0.40
    );*/
    0.40
    )」
    0.38
     ).
    0.38
     ").
    0.38
    Activations Density 0.386%

    No Known Activations