© 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. 7-GEMMASCOPE-RES-16K
    6. 16012
    Prev
    Next
    INDEX
    Explanations

    references to parameters and mappings in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.41
    cloudfront
    -0.35
    Poloha
    -0.34
    ChildScrollView
    -0.33
    Ho
    -0.33
    mspace
    -0.32
    addLast
    -0.32
     didReceive
    -0.32
    ://
    -0.32
    Cro
    -0.31
    POSITIVE LOGITS
     parameter
    2.63
     Parameter
    2.56
     parameters
    2.44
     Parameters
    2.41
    Parameter
    2.36
    parameter
    2.33
    Parameters
    2.25
    parameters
    2.22
     PARAMETER
    2.11
     PARAMETERS
    2.02
    Activations Density 0.110%

    No Known Activations