© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9560
    Prev
    Next
    INDEX
    Explanations

    references to specific people, events, or objects in a legal or formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    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
    vel
    -0.35
     pron
    -0.34
    acc
    -0.33
     Nis
    -0.31
     micro
    -0.31
     por
    -0.31
     mata
    -0.30
    soci
    -0.30
    oci
    -0.30
     Pont
    -0.30
    POSITIVE LOGITS
     esternos
    0.69
    Билгалдахарш
    0.65
     zijne
    0.65
     Italijani
    0.64
     dezelve
    0.63
     Biôgrafia
    0.63
    RUnlock
    0.63
     desmotivaciones
    0.62
     صوتيه
    0.61
     препратки
    0.60
    Activations Density 0.638%

    No Known Activations