Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1071
    Prev
    Next
    INDEX
    Explanations

    mathematical inequalities and comparisons

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

    LaTeX math mode expressions

    np_acts-logits-general · gemini-2.0-flash

    less than or equal to notation

    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
    cydow
    -0.58
     Speicher
    -0.57
     "','
    -0.57
    y
    -0.53
    ีก
    -0.51
    ("'
    -0.51
    world
    -0.50
     Gleich
    -0.49
    ("-
    -0.48
     getSession
    -0.48
    POSITIVE LOGITS
    ︎
    0.92
    ConstraintMaker
    0.91
    }';
    0.91
     препратки
    0.81
    URLException
    0.80
    }');
    0.74
    )';
    0.74
    }";
    0.70
    SceneManagement
    0.69
    ู่
    0.68
    Activations Density 0.433%

    No Known Activations