© 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. 18-GEMMASCOPE-RES-16K
    6. 6882
    Prev
    Next
    INDEX
    Explanations

    conversations and statements regarding unclear situations or ambiguity

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

    "something" or similar vague references

    np_acts-logits-general · gemini-2.0-flash

    or something like that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ']));
    -0.60
    "]);
    -0.55
    </tfoot>
    -0.53
    "])
    
    -0.49
    ()]);
    -0.49
    tır
    -0.46
    "]));
    -0.45
    "}}>
    -0.45
     }));
    -0.45
     Commencez
    -0.45
    POSITIVE LOGITS
     something
    2.08
    something
    1.96
    Something
    1.72
     Something
    1.63
     somewhere
    1.61
    somewhere
    1.46
     quelque
    1.42
     SOMETHING
    1.39
     somethin
    1.37
     Somewhere
    1.26
    Activations Density 0.284%

    No Known Activations