Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3716
    Prev
    Next
    INDEX
    Explanations

    references to proof and evidence in various contexts

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

    Mention of "proof" or "proof of concept"

    np_acts-logits-general · gemini-2.0-flash

    proof of concept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.78
    Портал
    -0.72
    canActivate
    -0.71
    Naissance
    -0.65
    theless
    -0.65
    }{*}{}
    -0.64
    yntaxException
    -0.63
    inales
    -0.61
     صوتيه
    -0.61
    lizes
    -0.61
    POSITIVE LOGITS
     noires
    0.69
     Proof
    0.63
     proofs
    0.59
    jalá
    0.56
    Proof
    0.55
    colección
    0.54
     proof
    0.54
    Evidence
    0.54
     positifs
    0.53
    reading
    0.53
    Activations Density 0.352%

    No Known Activations