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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14846
    Prev
    Next
    INDEX
    Explanations

    symbols and syntax used in coding, particularly related to programming logic and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PyExc
    -0.76
    stdc
    -0.66
     createSlice
    -0.65
    bitField
    -0.58
    writeField
    -0.57
    fromCharCode
    -0.57
    webElement
    -0.57
    thums
    -0.56
    InputBorder
    -0.56
    BufferException
    -0.55
    POSITIVE LOGITS
     tartalomajánló
    0.47
     bahía
    0.45
    AndEndTag
    0.44
     bluzka
    0.42
     <<<<<<<<<<<<<<
    0.42
    IntoConstraints
    0.38
     productivo
    0.38
     vacun
    0.37
     koszulka
    0.36
     bailarina
    0.35
    Activations Density 0.206%

    No Known Activations