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. 35-GEMMASCOPE-RES-16K
    6. 13967
    Prev
    Next
    INDEX
    Explanations

    phrases related to educational resources and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.50
    fortawesome
    -0.48
    Tikang
    -0.48
     firebaseConfig
    -0.44
     calldata
    -0.43
    saraba
    -0.42
    InsertCommand
    -0.42
    <?
    -0.41
    Ingrédients
    -0.41
    SBATCH
    -0.41
    POSITIVE LOGITS
     resources
    1.71
     resource
    1.49
    resources
    1.42
     Resources
    1.37
    Resources
    1.34
    resource
    1.24
     RESOURCES
    1.23
    资源
    1.23
     ressources
    1.22
     Resource
    1.18
    Activations Density 0.476%

    No Known Activations