© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 11275
    Prev
    Next
    INDEX
    Explanations

    terms related to different operational modes or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    springframework
    -0.68
    {{$
    -0.67
    ]--;
    -0.65
    сылкі
    -0.64
    ">{{$
    -0.63
     Puch
    -0.62
    )}</
    -0.62
     Becher
    -0.62
    ///</
    -0.61
    ************
    -0.61
    POSITIVE LOGITS
     Mode
    2.85
     mode
    2.79
    mode
    2.72
    Mode
    2.65
     modes
    2.55
     MODE
    2.50
    modes
    2.44
     Modes
    2.40
    MODE
    2.36
    Modes
    2.33
    Activations Density 0.051%

    No Known Activations