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. 8046
    Prev
    Next
    INDEX
    Explanations

    parameters related to configuration and limits for processes

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

    Values that represent maximums or limits

    np_acts-logits-general · gemini-2.0-flash

    set limits or maximum values

    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
    rungsseite
    -0.42
    ंदीखरीदारी
    -0.40
    OGND
    -0.38
     للاسماء
    -0.36
    ContentAsync
    -0.35
    addPreferredGap
    -0.35
     olduğu
    -0.33
     mergeFrom
    -0.32
    ɵɵ
    -0.32
    évaluateur
    -0.32
    POSITIVE LOGITS
     max
    1.52
     maximum
    1.52
     limit
    1.41
    max
    1.38
    Maximum
    1.34
    maximum
    1.32
     Maximum
    1.31
    Max
    1.30
     maksimal
    1.29
     Max
    1.28
    Activations Density 0.638%

    No Known Activations