© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4542
    Prev
    Next
    INDEX
    Explanations

    instances of blaming others for problems or failures

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

    blame or responsibility

    np_acts-logits-general · gemini-2.0-flash

    assigning blame or fault

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     core
    -0.34
    зья
    -0.34
     lenker
    -0.34
    scheduled
    -0.33
     library
    -0.33
     vak
    -0.33
     module
    -0.32
     Heter
    -0.31
    schedule
    -0.31
    Datuak
    -0.31
    POSITIVE LOGITS
     blame
    2.33
     blaming
    1.98
     blamed
    1.97
     blames
    1.93
    blame
    1.91
     Blame
    1.80
    Blame
    1.70
     culpa
    1.34
     scape
    1.30
     fault
    1.20
    Activations Density 0.439%

    No Known Activations