© 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. 24-GEMMASCOPE-RES-16K
    6. 1877
    Prev
    Next
    INDEX
    Explanations

    biological terms related to genetics and evolution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding verbs or pronouns

    np_acts-logits-general · gemini-2.0-flash

    genes encode proteins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.60
     its
    -0.58
    HasIndex
    -0.56
    rictions
    -0.56
     كومونز
    -0.56
    WriteTagHelper
    -0.55
    oly
    -0.53
    uspiel
    -0.52
    tets
    -0.52
    _=
    -0.52
    POSITIVE LOGITS
     range
    1.39
    each
    1.31
     each
    1.28
    range
    1.21
     ranged
    1.19
     ranges
    1.16
     collectively
    1.11
    Each
    1.03
     allemaal
    1.02
     ranging
    0.99
    Activations Density 0.582%

    No Known Activations