© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11099
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant endings or conclusions

    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
    395
    +0.13
    0.5%
    537
    +0.13
    0.5%
    1296
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    395
    +0.13
    0.06
    537
    +0.13
    0.05
    1296
    +0.13
    0.05
    Negative Logits
    chartInstance
    -0.51
    XmlAccessorType
    -0.48
     Dru
    -0.42
     Hentet
    -0.41
     FontWeight
    -0.40
    DispatchToProps
    -0.40
    presente
    -0.40
     pstmt
    -0.40
    kkelijk
    -0.40
    covite
    -0.40
    POSITIVE LOGITS
     End
    1.04
     end
    0.99
    End
    0.98
     END
    0.93
    end
    0.86
     Ends
    0.81
    END
    0.80
     endings
    0.78
    Ending
    0.77
    setEnd
    0.77
    Activations Density 0.099%

    No Known Activations