© 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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1276
    Prev
    Next
    INDEX
    Explanations

    conditional statements in programming code

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

    Code with conditional statements and expressions using brackets

    np_acts-logits-general · gemini-2.0-flash

    `if` statement conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     recomp
    -0.45
    NewGuid
    -0.44
    awtextra
    -0.44
    randomUUID
    -0.42
    IUrlHelper
    -0.42
    makeConstraints
    -0.42
    <>("
    -0.40
    AddTagHelper
    -0.40
     copro
    -0.40
     wrap
    -0.40
    POSITIVE LOGITS
     enamorado
    0.58
     apapun
    0.56
     tampoco
    0.55
     varsa
    0.54
     cualquiera
    0.54
     concernés
    0.53
     quelconque
    0.53
     crece
    0.52
     suficientemente
    0.52
     tirantes
    0.52
    Activations Density 0.172%

    No Known Activations