© 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. 17-GEMMASCOPE-RES-16K
    11. 5697
    Prev
    Next
    INDEX
    Explanations

    conditional statements and error handling constructs in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.68
    Spoljašnje
    -0.59
    yntaxException
    -0.58
    kloped
    -0.55
    axter
    -0.54
    prnewswire
    -0.53
    NgModule
    -0.52
     Bits
    -0.51
     Wicidata
    -0.51
    verläs
    -0.51
    POSITIVE LOGITS
    SharedCtor
    0.50
    Abstract
    0.49
    "".
    0.46
    Gal
    0.45
    AndEndTag
    0.44
     թվական
    0.44
    Eloquent
    0.43
    Wrap
    0.43
    Knows
    0.42
    angliski
    0.42
    Activations Density 0.119%

    No Known Activations