© 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. 38-GEMMASCOPE-RES-16K
    6. 8232
    Prev
    Next
    INDEX
    Explanations

    conditional statements and the necessity for action based on specific criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.55
    oa̍t
    -0.50
     MainAxisSize
    -0.48
    SourceChecksum
    -0.47
    StreetMap
    -0.46
    enderror
    -0.45
    $_['
    -0.44
    UpdateCommand
    -0.44
     Wicidata
    -0.44
    transQ
    -0.42
    POSITIVE LOGITS
     doing
    3.06
    Doing
    2.83
     Doing
    2.81
    doing
    2.64
     do
    2.20
     DOING
    2.19
     doin
    2.14
     done
    2.11
     hacerlo
    2.00
     melakukannya
    1.87
    Activations Density 2.153%

    No Known Activations