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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6658
    Prev
    Next
    INDEX
    Explanations

    references to the South or Southern regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bikini
    -0.47
    zzleHttp
    -0.46
     müſſen
    -0.45
    úgó
    -0.45
    abler
    -0.45
    fahrene
    -0.45
     cref
    -0.45
     (;;)
    -0.45
    commitment
    -0.44
    essler
    -0.44
    POSITIVE LOGITS
     South
    1.98
    South
    1.79
     SOUTH
    1.63
     south
    1.55
    south
    1.50
     North
    1.50
    SOUTH
    1.41
    North
    1.27
     north
    1.15
     NORTH
    1.14
    Activations Density 0.125%

    No Known Activations