© 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. 21-GEMMASCOPE-RES-16K
    6. 15853
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to data structure definitions and protocols

    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
    UrlResolution
    -0.48
    equity
    -0.47
     ujednoznacz
    -0.46
     CreateTagHelper
    -0.45
    #+#
    -0.45
     Equity
    -0.45
    fromnode
    -0.45
     nahilalakip
    -0.45
    Equity
    -0.44
    Péri
    -0.44
    POSITIVE LOGITS
    protobuf
    0.79
     ProtoMessage
    0.57
    protoc
    0.57
     jspb
    0.54
    Protobuf
    0.53
     iprot
    0.52
     protobuf
    0.51
     ErrIntOverflow
    0.51
     TType
    0.48
    exitRule
    0.47
    Activations Density 0.849%

    No Known Activations