© 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. 2-GEMMASCOPE-RES-16K
    11. 8154
    Prev
    Next
    INDEX
    Explanations

    references to damage or harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.59
     betweenstory
    -0.58
     المعيارى
    -0.54
    IsContent
    -0.49
    InputTagHelper
    -0.48
    +:+
    -0.47
    labelledby
    -0.44
     therewith
    -0.43
    AsUp
    -0.42
    AutoField
    -0.42
    POSITIVE LOGITS
     damage
    0.97
     Damage
    0.84
    damage
    0.81
     DAMAGE
    0.79
    Damage
    0.74
     harm
    0.73
     damaged
    0.66
    damaged
    0.60
    Harm
    0.59
     Harm
    0.58
    Activations Density 0.087%

    No Known Activations