© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 15658
    Prev
    Next
    INDEX
    Explanations

    elements related to image attributes, particularly alt text and width specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.97
    évaluateur
    -0.96
    parsedMessage
    -0.90
    OGND
    -0.87
    oredCriteria
    -0.87
    #+#
    -0.85
    \{\\
    -0.82
    يكب
    -0.81
     дописавши
    -0.80
     Monfieur
    -0.80
    POSITIVE LOGITS
     alt
    2.67
    alt
    1.94
     Alt
    1.88
    Alt
    1.84
     ALT
    1.57
    ALT
    1.54
     alts
    1.25
    alts
    0.96
     alta
    0.84
     al
    0.77
    Activations Density 0.060%

    No Known Activations