© 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. 10-GEMMASCOPE-RES-16K
    6. 6471
    Prev
    Next
    INDEX
    Explanations

    references to specific methods or techniques in a context, particularly in the domain of research or programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    󠁮
    -0.70
     posX
    -0.50
     πάνω
    -0.50
    Kauf
    -0.49
    Clair
    -0.49
    يكب
    -0.48
    randint
    -0.47
     pulumi
    -0.47
     signUp
    -0.47
     AssemblyVersion
    -0.46
    POSITIVE LOGITS
     Method
    2.03
     method
    2.00
    Method
    1.90
    method
    1.84
     METHOD
    1.77
     methods
    1.68
     Methods
    1.64
     méthode
    1.61
     método
    1.59
    METHOD
    1.55
    Activations Density 0.139%

    No Known Activations