© 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-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 1340
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and question marks, indicating sentence endings and inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -0.42
    }`;
    -0.28
    }';
    -0.27
    }`);
    -0.27
    }');
    -0.26
    }");
    -0.23
    >`;
    -0.22
    ftagPool
    -0.21
    >--}}
    -0.21
    "});
    -0.21
    POSITIVE LOGITS
    https
    1.01
    <eos>
    0.97
    http
    0.94
    Read
    0.89
    Copyright
    0.85
    Jul
    0.84
    <h1>
    0.82
    Source
    0.80
    <h3>
    0.80
    Tags
    0.79
    Activations Density 0.876%

    No Known Activations