© 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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13877
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming concepts like functions, methods, and code structure

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    876
    +0.22
    0.7%
    964
    +0.16
    0.5%
    872
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.22
    0.05
    876
    +0.16
    -0.01
    678
    +0.12
    0.04
    Negative Logits
    HtmlAttribute
    -0.70
     Meksiko
    -0.69
     feria
    -0.66
    ]!='
    -0.64
    Cyfarwyddwr
    -0.63
    __;
    -0.63
    ]));
    -0.62
    TProtocol
    -0.61
    PREFERRED
    -0.61
     Rptr
    -0.61
    POSITIVE LOGITS
     guarante
    2.44
     increa
    2.43
     maneu
    2.41
     scrat
    2.39
     impra
    2.29
     affor
    2.29
     encomp
    2.26
     intersper
    2.25
     snoopy
    2.19
     attemp
    2.18
    Activations Density 0.310%

    No Known Activations