© 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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1308
    Prev
    Next
    INDEX
    Explanations

    instances of calls to action, particularly "click here" prompts linked to additional information or resources

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

    "Click here for" links

    np_acts-logits-general · gemini-2.0-flash

    click here for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ])):
    -0.92
    Personensuche
    -0.90
    SBATCH
    -0.81
    ]));
    
    -0.79
    SEGUIR
    -0.79
    "];
    
    -0.77
    ])).
    -0.77
    '},
    
    -0.76
     يتيمه
    -0.76
    "):
    
    -0.75
    POSITIVE LOGITS
     link
    0.57
    !
    0.48
     referenties
    0.48
    url
    0.47
    http
    0.46
    link
    0.45
     pâte
    0.45
     LINK
    0.45
    or
    0.44
    をクリック
    0.43
    Activations Density 0.067%

    No Known Activations