© 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. 23-GEMMASCOPE-RES-16K
    11. 10097
    Prev
    Next
    INDEX
    Explanations

    terms related to depth and penetration 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
    AndEndTag
    -0.78
     فريبيس
    -0.65
    WithIOException
    -0.64
     nakalista
    -0.64
     Roskov
    -0.62
    KURZBESCHREIBUNG
    -0.61
    CloseOperation
    -0.59
    évaluateur
    -0.59
    entile
    -0.58
     виправивши
    -0.58
    POSITIVE LOGITS
     deep
    3.71
    deep
    3.30
     depth
    3.29
     deeper
    3.26
     Deep
    3.13
    Deep
    3.09
     deepest
    3.05
     DEEP
    2.96
    depth
    2.85
     depths
    2.85
    Activations Density 0.436%

    No Known Activations