© 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. 2-GEMMASCOPE-RES-16K
    6. 8702
    Prev
    Next
    INDEX
    Explanations

    phrases pertaining to listings or representations of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portail
    -0.60
     ब्रेकडाउन
    -0.52
    nologue
    -0.48
     AssemblyTitle
    -0.46
    ViewImports
    -0.45
    GeoNames
    -0.44
     chance
    -0.42
     endblock
    -0.42
    ransition
    -0.41
    tiba
    -0.41
    POSITIVE LOGITS
     mentioned
    2.05
     described
    1.88
     listed
    1.81
     outlined
    1.80
     indicated
    1.71
    mentioned
    1.71
     depicted
    1.64
    described
    1.64
     discussed
    1.61
     cited
    1.57
    Activations Density 0.363%

    No Known Activations