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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 11072
    Prev
    Next
    INDEX
    Explanations

    code snippets related to functions and method definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TestingModule
    -0.53
    Personendaten
    -0.47
     they
    -0.43
    AndEndTag
    -0.43
     ils
    -0.43
    elcome
    -0.42
     Schulz
    -0.41
    وازم
    -0.40
    createStatement
    -0.40
    hausen
    -0.40
    POSITIVE LOGITS
     noDo
    0.45
     auroit
    0.39
    adeira
    0.38
    CharCode
    0.37
     feroit
    0.36
     للمعارف
    0.36
    carteles
    0.36
    DetailActivity
    0.36
     her
    0.35
    __*/
    0.35
    Activations Density 0.368%

    No Known Activations