© 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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 14729
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a need for further research and evidence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagHelper
    -0.51
    ModelBuilder
    -0.51
    ोंने
    -0.51
    êcher
    -0.50
     كومونز
    -0.50
    rowser
    -0.49
    ButtonGroup
    -0.49
    RTLU
    -0.48
    mite
    -0.47
    UnusedPrivate
    -0.46
    POSITIVE LOGITS
     needed
    3.51
     required
    3.42
     necessary
    3.28
    needed
    3.06
    required
    2.99
     Needed
    2.94
     Required
    2.84
    necessary
    2.83
    Required
    2.71
     Necessary
    2.65
    Activations Density 1.137%

    No Known Activations