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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 4460
    Prev
    Next
    INDEX
    Explanations

    special characters and their frequency in the text

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

    Characters immediately preceding numbers or brackets

    np_acts-logits-general · gemini-2.0-flash

    mathematical or code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Бахар
    -0.54
    RegressionTest
    -0.51
    AndEndTag
    -0.50
    xnn
    -0.50
    forRoot
    -0.49
    WriteTagHelper
    -0.49
    (
    -0.48
    Jeografia
    -0.47
    "
    -0.47
    ỡng
    -0.46
    POSITIVE LOGITS
    ?}
    0.98
    `}
    0.96
    .}
    0.94
    $}
    0.94
    }\\
    0.93
    ]}
    0.88
    }</
    0.87
    -}
    0.86
    }
    
    0.86
    )}
    0.85
    Activations Density 0.104%

    No Known Activations