© 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. 2-GEMMASCOPE-RES-16K
    6. 8682
    Prev
    Next
    INDEX
    Explanations

    words related to attributes and blame

    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
    VolleyError
    -0.43
     elif
    -0.39
    лтамалар
    -0.39
    posedge
    -0.39
    AnimationsModule
    -0.37
    FirebaseDatabase
    -0.37
    ']);
    
    -0.36
    ServletException
    -0.35
    __((
    -0.35
    Веду
    -0.34
    POSITIVE LOGITS
     attributed
    1.45
     attribute
    1.33
     attributes
    1.20
    attributed
    1.13
     Attributes
    1.10
     blamed
    1.07
    Attributes
    1.05
    attributes
    1.04
     Attribute
    1.03
    attribute
    1.02
    Activations Density 0.068%

    No Known Activations