© 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-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 6140
    Prev
    Next
    INDEX
    Explanations

    recommendations and encouragements related to sharing and supporting others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GenerationType
    -0.58
    hadiran
    -0.48
     EdgeInsets
    -0.47
     '.';
    -0.47
    UVWXYZ
    -0.43
     ")";
    -0.43
    ])):
    -0.43
    imanapun
    -0.43
    ]));
    -0.42
     prévoir
    -0.42
    POSITIVE LOGITS
     friends
    2.16
     friend
    2.08
    friend
    1.82
    friends
    1.74
    Friend
    1.67
    Friends
    1.55
     Friend
    1.54
     Friends
    1.53
     colleague
    1.52
     FRIENDS
    1.48
    Activations Density 0.296%

    No Known Activations