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. 12-GEMMASCOPE-RES-16K
    6. 15802
    Prev
    Next
    INDEX
    Explanations

    dates and specific temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Suivez
    -0.48
     Geografía
    -0.47
    }');
    -0.45
    pgp
    -0.42
     logistique
    -0.42
     RSSSF
    -0.41
    ();)
    -0.41
    cámara
    -0.41
     ?',
    -0.41
     **/
    
    -0.40
    POSITIVE LOGITS
    setVerticalGroup
    1.07
    SourceChecksum
    0.94
    expandindo
    0.91
    VersionUID
    0.87
     AssemblyCompany
    0.81
    AndEndTag
    0.78
    OGND
    0.76
    parsedMessage
    0.75
    AsUp
    0.75
    CodeAttribute
    0.74
    Activations Density 0.746%

    No Known Activations